A framework to automate physical demand analysis based on artificial intelligence and motion capture for workplace safety improvement

  • Author / Creator
    Aliasgari, Ramin
  • Workers' safety and productivity and its affecting factors, such as ergonomics, are essential aspects of construction projects. Applying ergonomics and realizing the connections among workers and their assigned tasks have indicated a decrease in workers' injuries and discomforts, a beneficial effect on productivity, and a reduction in project costs. Workers in the construction zone are often subjected to awkward body postures and repetitive motions that cause musculoskeletal disorders. Accordingly, these disorders and circumstances lead to delays in production.
    This research focuses on an automated and systematic Physical Demand Analysis (PDA) via Artificial Intelligence (AI) and Motion Capture system (MOCAP) for analyzing the working circumstances associated with physical demand. It enables the health and safety department to comprehend the construction tasks and the plant operation in detail for each task and production line to analyze the potential ergonomic risks for workers. Conventionally, ergonomists use an expensive and long time process to manually gather data to fill out the forms associated with the PDA technique, which involves observing and interviewing the different workers about the physical demands of a particular job. No study has yet been conducted to make an automated framework based on construction 4.0 for this action. This study uses a MOCAP system and an artificial intelligence technique to obtain joint angles and body segment positions in different working situations, convert them to activities, and detect their frequency. The framework is created to automatically fill a posture-based PDA form and address the physiological side of the task demands. As a result, it can provide precise data about the physical demands of each job for different functions such as risk assessment, job matching, modified tasks for injured workers, and others. Also, the automated framework is created to reduce wastes related to costs and person-hours and improve the project's productivity.

  • Subjects / Keywords
  • Graduation date
    Fall 2022
  • Type of Item
  • Degree
    Master of Science
  • DOI
  • License
    This thesis is made available by the University of Alberta Library with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.